© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12762
    Prev
    Next
    INDEX
    Explanations

    about numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     וע
    1.53
     σύμφωνα
    1.19
     Dighe
    1.16
    ן
    1.16
     الذ
    1.13
     Diffraction
    1.13
     StyleSheet
    1.13
     ז
    1.09
     Dign
    1.08
     Disability
    1.03
    POSITIVE LOGITS
    idée
    1.41
    ਆਂ
    1.24
    sizes
    1.17
    ものを
    1.17
    dozen
    1.17
    무리
    1.16
     bunches
    1.15
    ething
    1.13
    вими
    1.13
    Replies
    1.13
    Activations Density 0.251%

    No Known Activations